A Dynamic Bayesian Network-Based Real-Time Crash Prediction Model for Urban Elevated Expressway

Abstract

Traffic crash is a complex phenomenon that involves coupling interdependency among multiple influencing factors. Considering that interdependency is critical for predicting crash risk accurately and contributes to revealing the underlying mechanism of crash occurrence as well, the present study attempts to build a Real-Time Crash Prediction Model (RTCPM) for urban elevated expressway accounting for the dynamicity and coupling interdependency among traffic flow characteristics before crash occurrence and identify the most probable risk propagation path and the most significant contributors to crash risk. In this study, Dynamic Bayesian Network (DBN) was the framework of the RTCPM. Random Forest (RF) method was employed to identify the most important variables, which were used to build DBN-based RTCPMs. The PC algorithm combined with expert experience was further applied to investigate the coupling interdependency among traffic flow characteristics in the DBN model. A comparative analysis among the improved DBN-based RTCPM considering the interdependency, the original DBN-based RTCPM without considering the interdependency, and Multilayer Perceptron (MLP) was conducted. Besides, the sensitivity and strength of influences analyses were utilized to identify the most probable risk propagation path and the most significant contributors to crash risk. The results showed that the improved DBN-based RTCPM had better prediction performance than the original DBN-based RTCPM and the MLP based RTCPM. The most probable risk influencing path was identified as follows: speed on current segment (V) (time slice 2)⟶V (time slice 1)⟶speed on upstream segment (U_V) (time slice 1)⟶Traffic Performance Index (TPI) (time slice 1)⟶crash risk on current segment. The most sensitive contributor to crash risk in this path was V (time slice 2), followed by TPI (time slice 1), V (time slice 1), and U_V (time slice 1). These results indicate that the improved DBN-based RTCPM has the potential to predict crashes in real time for urban elevated expressway. Besides, it contributes to revealing the underlying mechanism of crash and formulating the real-time risk control measures.

Severity Analysis of Hazardous Material Road Transportation Crashes with a Bayesian Network Using Highway Safety Information System Data

“…The global prediction of random forests is based on a majority vote on the predictions of each classification tree. It is a popular method for evaluating the significance of explanatory variables and variable selection in recent years [ 20 , 31 , 32 ]. Compared to many other commonly used classifiers, this method has proved to be performed very well and robust to overfitting [ 31 ].…”

“…Although conventional statistical methods have been proven effective in examining the relationships between HAZMAT crash severity and explanatory variables, they cannot reveal the underlying patterns and interplay of various factors [ 16 ]. In recent years, machine learning techniques, such as Bayesian networks [ 16 , 17 , 18 , 19 , 20 ], clustering [ 21 , 22 ], support vector machines [ 23 ], decision trees [ 4 , 24 ], random forests [ 25 , 26 ], and association mining rules [ 27 , 28 ] have been widely used for crash data analysis. These non-parameter approaches do not require assumption among explanatory variables, and they have been identified as having greater flexibility in supporting in-depth crash analysis and safety decision-making.…”

Accident Diagnosis and Evaluation System in Parking Lots Using Multisource Data Based on Bayesian Networks

“…Bayesian networks, on the other hand, are widely used because of their advantages in not requiring large amounts of data and their ability to refect the correlation and causal logic among multiple factors. Meanwhile, Bayesian can be fexibly combined with other methods to target some specifc problems [20][21][22], such as quality reliability analysis under Monte Carlo simulation [23] and risk ranking after random forest prediction results combined with Bayesian [21]. Te parking lot data sample is not particularly sufcient to fully refect the advantages of machine learning analysis, and we are aiming to understand the logical relationships between the factors.…”

Exploring the effects of stationary camera spots on inferences drawn from real-time crash severity models

“…Moreover, artificial intelligence methods as non-parametric techniques have been preferred by researchers to capture nonlinearities that exist between outcomes and explanatory variables. Different forms of neural networks 25 – 27 , Bayesian networks 5 , 28 , support vector machines 25 , 27 , and decision trees 24 , 29 – 31 are frequently proposed models among non-parametric techniques.…”